# Meta Muse Wonder API pricing, per agent task

Muse Wonder API pricing: Meta's per-token rates for muse-wonder-1.0, web search fees, rate limits, and the arithmetic for what one agent task costs.

## Summary

Muse Wonder API pricing is $4.00 per 1M input tokens, $0.20 per 1M cached input tokens and $20.00 per 1M output tokens for `muse-wonder-1.0` on the Meta Model API ([Meta's pricing page](https://dev.meta.ai/docs/pricing-rate-limits), read 2026-10-13). Web search grounding adds a fee per query. There is no cheaper Contributor mode for this model.

A price per token does not tell you what a task costs. An agent on Muse Wonder spends on two meters: tokens with Meta, and every data call it makes along the way. This post puts Meta's rates in one table, works through the arithmetic for one task with the token counts stated as an assumption, adds the data-call line, and lists the limits that cap your spend rate. Model facts come from [Meta's models page](https://dev.meta.ai/docs/models), read 2026-10-13.

## Muse Wonder API pricing at a glance

Meta bills text models per token on pay as you go, with no minimum and no upfront commitment. Muse Wonder has one price mode, Standard. Muse Spark sits on the same page for comparison, since Meta tells you to move work between the two by changing the model id.

| Model and mode | Input per 1M | Cached input per 1M | Output per 1M | Source |
|---|---|---|---|---|
| Muse Wonder, `muse-wonder-1.0`, Standard | $4.00 | $0.20 | $20.00 | Meta's pricing page, read 2026-10-13 |
| Muse Spark, Standard | $1.25 | $0.15 | $4.25 | Meta's pricing page, read 2026-10-13 |
| Muse Spark, Contributor | $0.10 | $0.002 | $0.20 | Meta's pricing page, read 2026-10-13 |

Four notes from the same page change the math:

- **Cached input** is billed when part of your prompt matches a cached prefix. The response's `cached_tokens` field says how many tokens that covered.
- **No long-context premium.** The rate is the same with a nearly empty or a nearly full context window, and Muse Wonder's window is 1,048,576 tokens.
- **Steering tokens are free.** Meta adds a small system prompt to every request and does not bill those tokens or count them in your usage.
- **Contributor mode is not available for Muse Wonder** on the API. Only Muse Spark 1.3 and 1.2 have it.

Muse Wonder is in preview, per Meta's models page, so these rates can change. Muse Wonder Full is not on the API at any price. It runs only in Muse Code on the Power Usage and Maximum Usage plans, and those plans are priced on [Meta's subscriptions page](https://dev.meta.ai/docs/muse-code/subscriptions), not per token.

## Muse Wonder API pricing per agent task: the arithmetic

Add up three token lines and the tool calls. The token counts below are an example we chose, not a measurement: a research task that reads 200,000 input tokens, of which 150,000 come from a cached prefix, writes 20,000 output tokens and runs 5 web searches through Meta's grounding.

| Line | Count | Cost | Source |
|---|---|---|---|
| Uncached input | 50,000 tokens | $0.20 | Meta's pricing page, read 2026-10-13 |
| Cached input | 150,000 tokens | $0.03 | Meta's pricing page, read 2026-10-13 |
| Output | 20,000 tokens | $0.40 | Meta's pricing page, read 2026-10-13 |
| Web search grounding | 5 queries | $0.0125 | Meta's pricing page, read 2026-10-13 |
| Total on Meta's bill |  | $0.6425 | Meta's pricing page, read 2026-10-13 |

Two things move this number most. Output is five times the input rate, so a task that writes long answers or long code costs more than one that reads a lot. Caching cuts the input rate to 5 percent of the uncached rate, so an agent that keeps its system prompt and tool list stable from call to call pays far less for the same context.

Your real counts come back in each response's usage object. Run one task, read the counts, and plug them in before you budget a thousand.

## The second line on the bill: data calls

Meta's built-in `web_search` tool costs $2.50 per 1,000 search queries on top of the request's tokens ([Meta's pricing page](https://dev.meta.ai/docs/pricing-rate-limits), read 2026-10-13). It applies to text models such as Muse Wonder and Muse Spark. When the task needs something else, the full text of a page, news results as rows or Google positions, your agent calls a data tool, and whoever serves it bills that call.

With looot, the agent calls those jobs from one prepaid balance and reads each price before it runs: `job:web.search`, `job:web.scrape.markdown`, `job:news.search` and `job:google.serp.organic`. The table reads the cheapest live price for each job from the looot catalog when the page loads.

Data calls for a Muse Wonder agent, cheapest live price. Prices read on 2026-10-14 from the live looot catalog. They change when a provider changes its price.

| Option | Cheapest provider | Price per call |
|---|---|---|
| Search the web | Firecrawl | $0.0010 per call |
| Read a page as markdown | Jina AI | $0.0002 per call |
| Search the news | Serper | $0.0010 per call |
| Google organic results | Serper | $0.0010 per call |

For the example task, add each price above times the number of calls. Searching and reading pages is covered job by job on the [web search API page](https://looot.ai/use-cases/web-search-api) and the [URL to markdown page](https://looot.ai/use-cases/url-to-markdown-api). The same two-meter view for any agent, not only Muse Wonder, is in [what an AI agent's data calls cost](https://looot.ai/blog/ai-agent-cost-data-calls), and the count-times-price math for lookups is in [what 1,000 lookups cost](https://looot.ai/blog/what-1000-lookups-cost).

This prompt prices the data side of one task without spending anything:

## Rate limits and caching on the Muse Wonder API

Rate limits cap how fast you can spend. For `muse-wonder-1.0`, Meta sets 3,000 requests per minute and 4,000,000 tokens per minute. The limits apply per team, not per API key, so every key in a team draws on the same budget, and each model has its own limits.

When you pass a limit, the API rejects the request with HTTP 429. Meta's advice is exponential backoff with jitter, starting near 500 ms, and waiting at least as long as any `Retry-After` header. Each response also carries `x-ratelimit-remaining-tokens` and `x-ratelimit-remaining-requests`, so an agent can slow down before it hits the wall.

Caching is the cheapest lever. Keep the stable parts of the prompt, the system prompt, tool definitions and long reference documents, at the start and unchanged, so later calls match the cached prefix and pay the cached rate.

## What this post cannot tell you

- **A measured task cost.** We did not run a Muse Wonder task for this post. The example uses token counts we chose.
- **Muse Code plan prices.** Muse Wonder Full is subscription only, and we quote no plan price here. Read [Meta's subscriptions page](https://dev.meta.ai/docs/muse-code/subscriptions).
- **Prices after the preview.** `muse-wonder-1.0` is in preview, so Meta can change the rates.
- **Where you can buy it.** Meta says model availability can vary by country, under its Geographic Use Policy.
- **Scheduled spend.** Running the same task on a timer needs scheduled runs, not available yet in looot.

Last checked 2026-10-13. Meta prices and limits were read that day from the Meta pages linked above. looot prices in the table are read from the live catalog when the page loads. More on the model itself is in [what is Muse Wonder](https://looot.ai/blog/what-is-meta-muse-wonder).

## Questions

### How much does Muse Wonder cost per million tokens?

On the Meta Model API it is $4.00 per 1M input tokens, $0.20 per 1M cached input tokens and $20.00 per 1M output tokens ([Meta's pricing page](https://dev.meta.ai/docs/pricing-rate-limits), read 2026-10-13). There is no long-context premium.

### Does Muse Wonder API pricing include web search?

No, web search grounding is billed on top of tokens, at $2.50 per 1,000 search queries ([Meta's pricing page](https://dev.meta.ai/docs/pricing-rate-limits), read 2026-10-13). Other data calls your agent makes are billed by whoever serves them.

### Is Muse Wonder Full available pay as you go?

No. Muse Wonder Full is not on the API. It runs only in Muse Code on the Power Usage and Maximum Usage plans, and setting reasoning effort to "max" on the API does not select it.

### Is there a cheaper Contributor mode for Muse Wonder?

No. Meta offers Contributor mode on the API only for Muse Spark 1.3 and 1.2. Muse Wonder runs in Standard mode, where your content is not used to train Meta models.

### Is Muse Wonder cheaper than Muse Spark?

No, Muse Spark costs less per token: $1.25 input and $4.25 output per 1M tokens in Standard mode ([Meta's pricing page](https://dev.meta.ai/docs/pricing-rate-limits), read 2026-10-13). Meta suggests Spark for high-volume or cost-sensitive work and Wonder for long, complex tasks.

### What are the Muse Wonder API rate limits?

3,000 requests and 4,000,000 tokens per minute for `muse-wonder-1.0`. The limits apply per team, across all its API keys.

### What do data calls cost for a Muse Wonder agent?

It depends on the job and the provider. The live table in this post reads the cheapest price for web search, page reading, news search and Google results from the looot catalog when the page loads, and your agent sees each price before it runs a call.

## For agents

### Code (bash)

```bash
cost = uncached_input x 4.00 / 1,000,000
     + cached_input   x 0.20 / 1,000,000
     + output         x 20.00 / 1,000,000
     + web_searches   x 2.50 / 1,000
```

### Price the data calls of one Muse Wonder task

```text
Use looot to price the data calls of one research task before my Muse Wonder agent runs it. First set up https://looot.ai/skill.md. Inspect the jobs web.search, web.scrape.markdown and news.search, and show me the price per call of the cheapest provider for each. Then estimate the data cost of one task that runs 2 web searches, reads 3 pages as markdown and runs 1 news search, and the cost of 100 such tasks. Do not run any paid call.
```